Apparatus and method for scent visualization

Abstract

A scent visualization system may comprise a display apparatus for generating a target image including a target object; an olfactory sensor for detecting a scent; and a scent visualization apparatus for generating target associative visualization information that reminds the scent from the target image received from the display apparatus and sensing information received from the olfactory sensor, and generating an associative image by combining the target associative visualization information and the target image. Therefore, a low-cost, high-efficiency, high-utilization, and high-convenience scent visualization system can be provided.

What is claimed is: 
     
       1. A scent visualization method of a scent visualization apparatus interworking with a display apparatus and an olfactory sensor, the scent visualization method comprising:
 receiving a target image including a target object from the display apparatus; 
 applying the target image to a first learning model; 
 generating first associative visualization information about the target image from the first learning model; 
 receiving sensing information from the olfactory sensor; 
 applying the sending information to a second learning model; 
 generating second associative visualization information on the sensing information from the second learning model; 
 comparing the first associative visualization information and the second associative visualization information to select a target associative visualization information having a higher similarity, the target associative visualization information being one selected between the first associative visualization information and the second associative visualization information; and 
 combining the selected target associative visualization information and the target image to generate an associative image. 
 
     
     
       2. The scent visualization method according to  claim 1 , wherein the first learning model is generated through machine learning by extracting visualization information representing first basic data which is olfactory sensibility information of the target object with visual attribute information, and extracting the first associative visualization information having a high similarity among the visualization information. 
     
     
       3. The scent visualization method according to  claim 2 , wherein the second learning model is generated through machine learning by extracting visualization information representing second basic data which is olfactory sensitivity information of the sensing information with visual attribute information, and extracting the second associative visualization information having a high similarity among the visualization information. 
     
     
       4. The scent visualization method according to  claim 3 , wherein the visualization information is represented by at least one of an attribute representing a particle effect, an icon, an illustration, a photograph, and a constellation. 
     
     
       5. The scent visualization method according to  claim 3 , wherein the first associative visualization information and the second associative visualization information are extracted using a softmax algorithm. 
     
     
       6. The scent visualization method according to  claim 1 , wherein the display apparatus is a head mounted display (HMD) apparatus. 
     
     
       7. The scent visualization method according to  claim 1 , further comprising generating a least one scent corresponding to the sensing information by interworking with a scent diffusion apparatus. 
     
     
       8. A scent visualization apparatus comprising a processor and a memory storing at least one instruction executable by the processor, wherein when executed by the processor, the at least one instruction is configured to:
 interwork with a display apparatus and an olfactory sensor; 
 receive a target image including a target object from the display apparatus; 
 receive sensing information from the olfactory sensor; 
 output first associative visualization information about the target image using a first learning model to which the target image is applied; 
 output second associative visualization information about the sensing information using a second learning model to which the sensing information is applied; 
 compare the first associative visualization information and the second associative visualization information to select a target associative visualization information having a higher similarity, the target associative visualization information being one selected between the first associative visualization information and the second associative visualization information; and 
 combine the selected target associative visualization information and the target image to generate an associative image. 
 
     
     
       9. The scent visualization apparatus according to  claim 8 , further comprising a communication unit providing a communication network for interworking with the display apparatus and the olfactory sensor. 
     
     
       10. The scent visualization apparatus according to  claim 8 , further comprising a storage unit for storing data, wherein the storage unit comprises:
 a first storage unit storing first basis data which is olfactory sensibility information of the target image; 
 a second storage unit storing second basic data which is olfactory sensibility information of the sensing information; and 
 a third storage unit storing the first learning model and the second learning model. 
 
     
     
       11. The scent visualization apparatus according to  claim 8 , wherein the at least one instruction is further configured to:
 learn the first basic data; 
 learn the second basic data; 
 generate the first learning model; and 
 generate the second learning model. 
 
     
     
       12. The scent visualization apparatus according to  claim 8 , wherein the first learning model is generated through machine learning by extracting visualization information representing the first basic data with visual attribute information, and extracting the first associative visualization information having a high similarity among the visualization information. 
     
     
       13. The scent visualization apparatus according to  claim 12 , wherein the second learning model is generated through machine learning by extracting visualization information representing the second basic data with visual attribute information, and extracting the second associative visualization information having a high similarity among the visualization information. 
     
     
       14. The scent visualization apparatus according to  claim 13 , wherein the visualization information is represented by at least one of an attribute representing a particle effect, an icon, an illustration, a photograph, and a constellation. 
     
     
       15. The scent visualization apparatus according to  claim 13 , wherein the first associative visualization information and the second associative visualization information are extracted using a softmax algorithm. 
     
     
       16. The scent visualization apparatus according to  claim 8 , wherein the display apparatus is a head mounted display (HMD) apparatus. 
     
     
       17. The scent visualization apparatus according to  claim 8 , wherein the at least one instruction is further configured to generate a least one scent corresponding to the sensing information by interworking with a scent diffusion apparatus. 
     
     
       18. A scent visualization system comprising:
 a display apparatus for generating a target image including a target object; 
 an olfactory sensor for detecting a scent; and 
 a scent visualization apparatus for generating a target associative visualization information that reminds the scent from the target image received from the display apparatus and sensing information received from the olfactory sensor, and generating an associative image by combining the target associative visualization information and the target image, 
 wherein first associative visualization information about the target image is output using a first learning model to which the target image is applied, second associative visualization information about the sensing information is output using a second learning model to which the sensing information is applied, and associative visualization information having a higher similarity between the first associative visualization information and the second associative visualization information is selected as the target associative visualization information. 
 
     
     
       19. The scent visualization system according to  claim 18 , further comprising a scent diffusion apparatus generating at least one scent corresponding to the sensing information.